Add dino embeddings for offline inference

dinov2/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "facebook/dinov2-base",
+  "apply_layernorm": true,
+  "architectures": [
+    "Dinov2Model"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "drop_path_rate": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "image_size": 518,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "out_features": [
+    "stage12"
+  ],
+  "out_indices": [
+    12
+  ],
+  "patch_size": 14,
+  "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "use_swiglu_ffn": false
+}

dinov2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73036b56966966d07975d696bde331762f37297e2f095de8cea0040c3aa0841
+size 346345912

dinov2/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "BitImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}

save_pretrained.py

@@ -0,0 +1,10 @@
+from transformers import AutoImageProcessor, AutoModel
+
+if __name__ == "__main__":
+    model_name = "facebook/dinov2-base"
+    processor = AutoImageProcessor.from_pretrained(model_name)
+    model = AutoModel.from_pretrained(model_name)
+
+    # save pretrained
+    processor.save_pretrained("dinov2")
+    model.save_pretrained("dinov2")

script.py

@@ -41,7 +41,7 @@ class LinearClassifier(nn.Module):
 
 
 class TransformDino:
-    def __init__(self, model_name="facebook/dinov2-base"):
+    def __init__(self, model_name="./dinov2"):
         self.processor = AutoImageProcessor.from_pretrained(model_name)
         self.model = AutoModel.from_pretrained(model_name)